计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (22): 180-182.

• 图形、图像、模式识别 • 上一篇    下一篇

基于改进测地线模型的医学图像分割

郑 伟1，孙淳晔1，张晓丹2，马泽鹏2   

  1. 1.河北大学 电子信息工程学院，河北 保定 071002
    2.河北大学 医学部，河北 保定 071002
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-08-01 发布日期:2011-08-01

Medical image segmentation based on improved GAC model

ZHENG Wei1，SUN Chunye1，ZHANG Xiaodan2，MA Zepeng2   

  1. 1.College of Electronic and Information Engineering，Hebei University，Baoding，Hebei 071002，China
    2.Hebei University Health Science Center，Baoding，Hebei 071002，China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-08-01 Published:2011-08-01

PDF

摘要： 提出了一种由测地线活动轮廓模型GAC（Geodesic Active Contour）和局部区域信息相结合的图像分割新方法LGAC（Local Geodesic Active Contour）。构造了基于图像局部信息的演化曲线符号压力函数和演化模型，用水平集方法演化实现，零水平集能准确地在目标边缘收敛，对目标背景对比度较低的图像的分割达到理想效果。利用高斯核函数对水平集函数平滑处理以维持演化稳定，节省了计算时间。实验结果证明了该方法的可行性。

关键词: 图像分割, 测地线活动轮廓模型, 水平集, 符号压力函数

Abstract: This paper proposes a novel method of image segmentation，LGAC（Local Geodesic Active Contour）.It is based on the combination of the model of geodesic active contour with the local area information.The sign pressure function of the evolution curve based on the local area and the new evolution model are constructed.The method is implemented by the level set and the zero level set can converge in the boundary accurately.This method can achieve ideal effect for image segmentation of low contrast.The paper adopts Gaussian kernel function to regulate the level set for its smoothness and stability which saves computing time.The experimental results confirm the feasibility.

Key words: image segmentation, Geodesic Active Contour（GAC）, level set, sign pressure function

京ICP备13024262号-1
Copyright © 《计算机工程与应用》编辑部
技术支持：北京玛格泰克科技发展有限公司
总访问量
今日访问
在线人数